Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

NCS and MS-based similar object real-time detection method and system

A technology for real-time detection of objects, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as high cost and achieve high real-time effects

Active Publication Date: 2020-09-11
GUIZHOU POWER GRID CO LTD
View PDF12 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, in the field of image detection, object detection technologies based on image workstations or network services, magnetic field sensors, and neural computing sticks have been very mature, but in some specific industrial production scenarios, it is necessary for the Objects are detected in real time, and the specific corresponding numbered objects of the objects are identified, and their process data is stored, which cannot be satisfied by the traditional single-camera object detection technology.
[0003] Traditional multi-object real-time detection needs to correspond to multiple cameras, and use the network to transmit data in real time to an image workstation with a high-end GPU for real-time detection, which is extremely expensive for large-scale industrial applications

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • NCS and MS-based similar object real-time detection method and system
  • NCS and MS-based similar object real-time detection method and system
  • NCS and MS-based similar object real-time detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Object detection is a core research issue of computer vision, and it has been widely used in the fields of visual environment perception, intelligent video analysis, image detection, etc. Influencing factors such as rigid deformation, local occlusion, and complex backgrounds cause large changes in the appearance characteristics of objects, which bring great challenges and uncertainties to object detection algorithms.

[0035] refer to figure 1 , figure 2 and image 3 , which is the first embodiment of the present invention, this embodiment provides a real-time detection method for similar objects based on NCS and MS, including:

[0036] S1: Collect image data of similar objects for preprocessing, extract edge feature parameters to construct a sample data set. It should be noted that preprocessing image data includes:

[0037] Eliminate the noise points of the image data, set the detection value, and sequentially detect the pixels in the image data;

[0038] Compar...

Embodiment 2

[0102] refer to Figure 4 , which is the second embodiment of the present invention. This embodiment is different from the first embodiment in that it provides a real-time detection system for similar objects based on NCS and MS, including:

[0103] The collection module 100 is used to collect image data of similar objects, which includes a camera 101 and a magnetic field sensor 102. The camera 101 is used to detect and shoot pictures of similar objects in real time, and the magnetic field sensor 102 is used to capture the rotation angle of the data collected by the camera 101 in real time.

[0104] The image sensing module 200 is connected with the camera 101 , and is used to acquire the photographed pictures of similar objects, perform feature processing on them, recognize them, convert them into image data, and transmit them to the core processing module 300 .

[0105] The core processing module 300 is used to uniformly calculate and process the image data and the rotation ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an NCS and MS-based similar object real-time detection method and system, and the method comprises: collecting the image data of a similar object, carrying out the preprocessing, extracting edge feature parameters, and constructing a sample data set; inputting the sample data set into a recognition model for training, ending the training until a training precision thresholdis met, and outputting a recognition result; performing detection classification of corresponding object numbers on the identification result by using a decision model, advancing a detection processin real time in combination with an AI accelerator, and outputting a corresponding detection result; and importing the detection result into a Bayesian analysis model to carry out secondary verification judgment, and displaying the verification result and the detection result in real time by using a mobile terminal or a Raspberry Pi display. According to the method, the image detection object canbe rapidly propelled and the specific object of the object can be identified so that the problem that the specific object cannot be judged in the process of image detection of multiple similar objectscan be solved, and the method has relatively high real-time performance, accuracy, applicability and economy.

Description

technical field [0001] The invention relates to the technical field of image detection, in particular to a method and system for real-time detection of similar objects based on NCS and MS. Background technique [0002] At present, in the field of image detection, object detection technologies based on image workstations or network services, magnetic field sensors, and neural computing sticks have been very mature, but in some specific industrial production scenarios, it is necessary for the The object is detected in real time, and the specific corresponding numbered object of the object is identified, and its process data is stored, which cannot be satisfied by the traditional single-camera object detection technology. [0003] Traditional multi-object real-time detection needs to correspond to multiple cameras, and use the network to transmit data in real time to an image workstation with a high-end GPU for real-time detection, which is extremely expensive for large-scale i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/2411G06F18/24155G06F18/214
Inventor 王元峰杨凤生王林波曾惜杨金铎王恩伟王冕王宏远刘畅兰雯婷熊萱龙思璇马庭桦付滨
Owner GUIZHOU POWER GRID CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com